Image Defect Extraction Using Directional Filtering and Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current image processing methods for determining the cause of image defects in image forming devices are complex and inefficient, particularly when dealing with multiple types of defects in a test image, as they require extensive processing and large amounts of training data to achieve accurate results.
Innovation Solution
An image processing method that generates preprocessed images by applying filters in both horizontal and vertical directions to emphasize pixel value differences, allowing for the extraction of singular parts as image defects, and uses pattern recognition techniques to determine the cause of these defects with reduced computational load.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional image processing methods are used to determine the cause of image defects, then determination accuracy can be achieved, but the processing complexity and time consumption increase significantly
Solution Approach 1:
The test image is divided into multiple blocks, and each block is processed independently to extract singular parts. This segmentation approach reduces the overall processing complexity by breaking down the complex task of analyzing the entire image into simpler, manageable sub-tasks, while maintaining determination accuracy through systematic analysis of each segment
Solution Approach 2:
The invention extracts singular parts (image defects) from the test image by comparing pixel values with reference values and identifying deviations. This extraction process isolates the essential defect information from the complex image data, enabling accurate cause determination without processing the entire image in detail
2Measurement precision
If conventional image processing methods are used to determine the cause of image defects, then determination accuracy can be achieved, but the processing time increases
Solution Approach 1:
Reference images are pre-generated for each type of image defect, storing the characteristic pixel values of various defects. This preliminary preparation allows the processing system to quickly compare test image blocks against known defect patterns without performing complex analysis during the actual defect detection, significantly reducing processing time while maintaining accuracy
Solution Approach 2:
The test image is divided into multiple blocks that are processed in parallel or sequence. This segmentation enables faster processing by limiting the analysis scope to small, manageable blocks rather than analyzing the entire large image at once, thereby reducing total processing time while maintaining comprehensive defect detection
3Adaptability or versatility
If the test image includes multiple types of image defects, then comprehensive defect detection is achieved, but the determination process becomes more complex
Solution Approach 1:
The test image containing multiple defect types is divided into blocks, and each block is independently analyzed to identify its specific defect type. This segmentation allows the system to handle multiple defect types systematically by processing each block through the same standardized procedure, simplifying the overall determination process while maintaining comprehensive defect detection coverage
Solution Approach 2:
A universal processing method is applied to all blocks of the test image, where the same steps (comparing pixel values with reference values, identifying singular parts) are used regardless of the defect type. This universal approach enables the system to detect and classify multiple defect types using a single, standardized process, reducing complexity while maintaining versatility
Data Source
AI summary
An object of the present invention is to extract image defects from a test image for each type by a simple process. A processor (80) generates a first preprocessed image and a second preprocessed image by executing a main filter process with each of a horizontal direction and a vertical direction of the test image used as a processing direction. The main filter process is a process of converting the pixel value of each pixel of interest sequentially selected from the test image into a converted value obtained by a process of emphasizing the difference between the pixel values of an area of interest and the pixel values of two adjacent areas. The processor (80) extracts, as the image defects, a first singular part that is present in the first preprocessed image and is not common to both images, a second singular part that is present in the second preprocessed image and is not common to both images, and a third singular part that is common to both images.